A PAC RL Algorithm for Episodic POMDPs

TL;DR

This paper introduces a novel PAC RL algorithm for episodic POMDPs that achieves polynomial sample complexity bounds, advancing efficient learning in partially observable environments.

Contribution

It presents the first RL algorithm with polynomial sample complexity for a significant class of episodic POMDPs, leveraging recent latent variable estimation techniques.

Findings

Achieves polynomial bounds on episodes for near-optimal performance

Applicable to an important class of episodic POMDPs

Builds on recent advances in method of moments for latent variable models

Abstract

Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially observable RL algorithm with a polynomial bound on the number of episodes on which the algorithm may not achieve near-optimal performance. Our algorithm is suitable for an important class of episodic POMDPs. Our approach builds on recent advances in method of moments for latent variable model estimation.